Enhancing building extraction from remote sensing images through UNet and transfer learning

被引:2
作者
Ait El Asri S. [1 ]
Negabi I. [1 ]
El Adib S. [1 ]
Raissouni N. [1 ]
机构
[1] Remote Sensing Systems and Telecommunications, National School for Applied Sciences, University Abdelmalek Essaadi, Tetuan
关键词
Building extraction; Remote sensing images; ResNet; transfer learning; UNet;
D O I
10.1080/1206212X.2023.2219117
中图分类号
学科分类号
摘要
Performing accurate extraction of buildings from remote sensing (RS) images is a crucial process with widespread applications in urban planning, disaster management, and urban monitoring. However, this task remains challenging due to the diversity and complexity of building shapes, sizes, and textures, as well as variations in lighting and weather conditions. These difficulties motivate our research to propose an improved approach for building extraction using UNet and transfer learning to address these challenges. In this work, we tested seven different backbone architectures within the UNet encoder and found that combining UNet with ResNet101 or ResNet152 yielded the best results. Based on these findings, we combined the superior performance of these base models to create a novel architecture, which achieved significant improvements over previous methods. Specifically, our method achieved a 1.33% increase in Intersection over Union (IoU) compared to the baseline UNet model. Furthermore, it demonstrated a superior performance with a 1.21% increase in IoU over UNet-ResNet101 and a 1.60% increase in IoU over UNet-ResNet152. We evaluated our proposed approach on the INRIA Aerial Image dataset and demonstrated its superiority. Our research addresses a critical need for accurate building extraction from RS images and overcomes the challenges posed by diverse building characteristics. © 2023 Informa UK Limited, trading as Taylor & Francis Group.
引用
收藏
页码:413 / 419
页数:6
相关论文
共 50 条
[21]   Building Extraction From Remote Sensing Images With DoG as Prior Constraint [J].
Quan, Yujun ;
Yu, Anzhu ;
Cao, Xuefeng ;
Qiu, Chunping ;
Zhang, Xiaoyi ;
Liu, Bing ;
He, Peipei .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 :6559-6570
[22]   Homogeneous Aggregation Convolution for Building Extraction From Remote Sensing Images [J].
Zhang, Rouyu ;
Lin, Baokai ;
Zhang, Qian ;
Zhang, Guixu .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
[23]   SEMANTIC ALIGNMENT NETWORK FOR BUILDING EXTRACTION FROM REMOTE SENSING IMAGES [J].
Fu, Wei ;
Xie, Kai ;
Du, Xingbei ;
Fang, Leyuan .
2024 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2024), 2024, :8127-8130
[24]   AFL-Net: Attentional Feature Learning Network for Building Extraction from Remote Sensing Images [J].
Qiu, Yue ;
Wu, Fang ;
Qian, Haizhong ;
Zhai, Renjian ;
Gong, Xianyong ;
Yin, Jichong ;
Liu, Chengyi ;
Wang, Andong .
REMOTE SENSING, 2023, 15 (01)
[25]   MSTrans: Multi-Scale Transformer for Building Extraction from HR Remote Sensing Images [J].
Yang, Fei ;
Jiang, Fenlong ;
Li, Jianzhao ;
Lu, Lei .
ELECTRONICS, 2024, 13 (23)
[26]   Capsule-Encoder-Decoder: A Method for Generalizable Building Extraction from Remote Sensing Images [J].
Tang, Zhenchao ;
Chen, Calvin Yu-Chian ;
Jiang, Chengzhen ;
Zhang, Dongying ;
Luo, Weiran ;
Hong, Zhiming ;
Sun, Huaiwei .
REMOTE SENSING, 2022, 14 (05)
[27]   Pixel-Level Self-Supervised Learning for Semi-Supervised Building Extraction From Remote Sensing Images [J].
Yu, Anzhu ;
Liu, Bing ;
Cao, Xuefeng ;
Qiu, Chunping ;
Guo, Wenyue ;
Quan, Yujun .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
[28]   E-Unet: a atrous convolution-based neural network for building extraction from high-resolution remote sensing images [J].
He Z. ;
Ding H. ;
An B. .
Cehui Xuebao/Acta Geodaetica et Cartographica Sinica, 2022, 51 (03) :457-467
[29]   C-UNet: Complement UNet for Remote Sensing Road Extraction [J].
Hou, Yuewu ;
Liu, Zhaoying ;
Zhang, Ting ;
Li, Yujian .
SENSORS, 2021, 21 (06) :1-21
[30]   AGs-Unet: Building Extraction Model for High Resolution Remote Sensing Images Based on Attention Gates U Network [J].
Yu, Mingyang ;
Chen, Xiaoxian ;
Zhang, Wenzhuo ;
Liu, Yaohui .
SENSORS, 2022, 22 (08)